A Survey on Gender Classification and Age Prediction Hybrid Models Based on Deep Learning Techniques
Author : Vinit Pannalal Balbhadre, Nitesh Gupta and Anurag Srivastava
Abstract :
Age and gender prediction from visual data have gained significant attention in computer vision research due to their wide-ranging applications in various domains such as marketing, healthcare, and security. This survey investigates the landscape of gender classification and age prediction hybrid models, focusing on their foundation in deep learning techniques. With the proliferation of deep learning methodologies, these models have garnered considerable attention for their applications in diverse domains, ranging from security systems to targeted advertising. Through an extensive examination of existing literature, this survey elucidates the advancements, challenges, and future prospects of such models. Key findings reveal the strides made in developing robust hybrid models, alongside persistent challenges related to data bias, interpretability, and generalization. Moreover, the survey underscores the importance of considering social and ethical implications in the deployment of these models, advocating for interdisciplinary collaboration and ethical guidelines. By synthesizing current research, this survey offers insights into the evolving landscape of gender classification and age prediction, serving as a foundation for future advancements and responsible deployment of deep learning-based hybrid models.
Keywords :
CNN, Age Prediction, Gender Classification, Deep Learning, Recurrent neural network (RNN), Pre-processing, Feature Selection.
